Please use this identifier to cite or link to this item:
|Title:||A hybrid morpheme-word representation for machine translation of morphologically rich languages||Authors:||Luong, M.-T.
|Issue Date:||2010||Citation:||Luong, M.-T.,Nakov, P.,Kan, M.-Y. (2010). A hybrid morpheme-word representation for machine translation of morphologically rich languages. EMNLP 2010 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference : 148-157. ScholarBank@NUS Repository.||Abstract:||We propose a language-independent approach for improving statistical machine translation for morphologically rich languages using a hybrid morpheme-word representation where the basic unit of translation is the morpheme, but word boundaries are respected at all stages of the translation process. Our model extends the classic phrase-based model by means of (1) word boundary-aware morpheme-level phrase extraction, (2) minimum error-rate training for a morpheme-level translation model using word-level BLEU, and (3) joint scoring with morpheme- and word-level language models. Further improvements are achieved by combining our model with the classic one. The evaluation on English to Finnish using Europarl (714K sentence pairs; 15.5M English words) shows statistically significant improvements over the classic model based on BLEU and human judgments. © 2010 Association for Computational Linguistics.||Source Title:||EMNLP 2010 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference||URI:||http://scholarbank.nus.edu.sg/handle/10635/41304||ISBN:||1932432868|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.